基于Transformer网络的配电网强化学习方法(PDN)高带宽存储器优化(HBM)
Transformer Network-based Reinforcement Learning Method for Power Distribution Network (PDN) Optimization of High Bandwidth Memory (HBM)
摘要:
本文首次提出了一种基于Transformer网络的强化学习(RL)方法用于高带宽存储器(HBM)的配电网(PDN)优化。所提出的方法可以提供最佳去耦电容器(decap)设计,以最大化在多个端口处看到的PDN自阻抗和转移阻抗的减小。实现了一种基于注意力的Transformer网络,直接参数化开盖优化策略。由于注意力机制具有强大的表达式,可以为decap分配探索大量的组合空间,因此最优性性能得到了显着改善。此外,它可以捕获开盖分配之间的顺序关系。由于在探测端口和开盖分配候选者的位置上的可重用网络,用于优化的计算时间显著减少。这是因为Transformer网络具有上下文嵌入过程以捕获包括探测端口位置的元特征。此外,网络是用随机生成的数据集训练的。因此,无需额外的训练,经过训练的网络就可以解决新的开盖优化问题。由于网络的可扩展性,训练和数据成本的计算时间大大减少。由于其共享权重属性,该网络可以适应更大规模的问题,而无需额外的训练。为了验证,我们将结果与传统的遗传算法(GA),随机搜索(RS),和所有以前的RL为基础的方法。结果表明,该方法在最优性、计算时间和数据效率等方面都有较好的性能。
英文摘要:
In this article, for the first time, we propose a transformer network-based reinforcement learning (RL) method for power distribution network (PDN) optimization of high bandwidth memory (HBM). The proposed method can provide an optimal decoupling capacitor (decap) design to maximize the reduction of PDN self- and transfer impedance seen at multiple ports. An attention-based transformer network is implemented to directly parameterize decap optimization policy. The optimality performance is significantly improved since the attention mechanism has powerful expression to explore massive combinatorial space for decap assignments. Moreover, it can capture sequential relationships between the decap assignments. The computing time for optimization is dramatically reduced due to the reusable network on positions of probing ports and decap assignment candidates. This is because the transformer network has a context embedding process to capture meta-features including probing ports positions. In addition, the network is trained with randomly generated data sets. Therefore, without additional training, the trained network can solve new decap optimization problems. The computing time for training and data cost are critically decreased due to the scalability of the network. Thanks to its shared weight property, the network can adapt to a larger scale of problems without additional training. For verification, we compare the results with conventional genetic algorithm (GA), random search (RS), and all the previous RL-based methods. As a result, the proposed method outperforms in all the following aspects: optimality performance, computing time, and data efficiency.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。